利用深度学习从水下视频中检测和计算牛蛙的数量

IF 3.1 2区农林科学 Q1 FISHERIES

ICES Journal of Marine Science Pub Date : 2024-07-23 DOI:10.1093/icesjms/fsae089

Antoni Burguera Burguera, Francisco Bonin-Font, Damianos Chatzievangelou, Maria Vigo Fernandez, Jacopo Aguzzi

{"title":"利用深度学习从水下视频中检测和计算牛蛙的数量","authors":"Antoni Burguera Burguera, Francisco Bonin-Font, Damianos Chatzievangelou, Maria Vigo Fernandez, Jacopo Aguzzi","doi":"10.1093/icesjms/fsae089","DOIUrl":null,"url":null,"abstract":"The Norway lobster (Nephrops norvegicus) is one of the most important fishery items for the EU blue economy. This paper describes a software architecture based on neural networks, designed to identify the presence of N. norvegicus and estimate the number of its individuals per square meter (i.e. stock density) in deep-sea (350–380 m depth) Fishery No-Take Zones of the northwestern Mediterranean. Inferencing models were obtained by training open-source networks with images obtained from frames partitioning of in submarine vehicle videos. Animal detections were also tracked in successive frames of video sequences to avoid biases in individual recounting, offering significant success and precision in detection and density estimations.","PeriodicalId":51072,"journal":{"name":"ICES Journal of Marine Science","volume":"82 1","pages":""},"PeriodicalIF":3.1000,"publicationDate":"2024-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Deep learning for detection and counting of Nephrops norvegicus from underwater videos\",\"authors\":\"Antoni Burguera Burguera, Francisco Bonin-Font, Damianos Chatzievangelou, Maria Vigo Fernandez, Jacopo Aguzzi\",\"doi\":\"10.1093/icesjms/fsae089\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The Norway lobster (Nephrops norvegicus) is one of the most important fishery items for the EU blue economy. This paper describes a software architecture based on neural networks, designed to identify the presence of N. norvegicus and estimate the number of its individuals per square meter (i.e. stock density) in deep-sea (350–380 m depth) Fishery No-Take Zones of the northwestern Mediterranean. Inferencing models were obtained by training open-source networks with images obtained from frames partitioning of in submarine vehicle videos. Animal detections were also tracked in successive frames of video sequences to avoid biases in individual recounting, offering significant success and precision in detection and density estimations.\",\"PeriodicalId\":51072,\"journal\":{\"name\":\"ICES Journal of Marine Science\",\"volume\":\"82 1\",\"pages\":\"\"},\"PeriodicalIF\":3.1000,\"publicationDate\":\"2024-07-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"ICES Journal of Marine Science\",\"FirstCategoryId\":\"97\",\"ListUrlMain\":\"https://doi.org/10.1093/icesjms/fsae089\",\"RegionNum\":2,\"RegionCategory\":\"农林科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"FISHERIES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"ICES Journal of Marine Science","FirstCategoryId":"97","ListUrlMain":"https://doi.org/10.1093/icesjms/fsae089","RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"FISHERIES","Score":null,"Total":0}

引用次数: 0

摘要

挪威龙虾（Nephrops norvegicus）是欧盟蓝色经济中最重要的渔业资源之一。本文介绍了一种基于神经网络的软件架构，旨在识别挪威龙虾的存在，并估算其在地中海西北部深海（350-380 米深）渔业禁捕区每平方米的个体数量（即种群密度）。推理模型是通过对潜水器视频中的帧分割图像进行开源网络训练获得的。此外，还对连续帧视频序列中的动物探测进行了跟踪，以避免单个重述中的偏差，从而在探测和密度估算方面取得了显著的成功和精确度。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Deep learning for detection and counting of Nephrops norvegicus from underwater videos

The Norway lobster (Nephrops norvegicus) is one of the most important fishery items for the EU blue economy. This paper describes a software architecture based on neural networks, designed to identify the presence of N. norvegicus and estimate the number of its individuals per square meter (i.e. stock density) in deep-sea (350–380 m depth) Fishery No-Take Zones of the northwestern Mediterranean. Inferencing models were obtained by training open-source networks with images obtained from frames partitioning of in submarine vehicle videos. Animal detections were also tracked in successive frames of video sequences to avoid biases in individual recounting, offering significant success and precision in detection and density estimations.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

ICES Journal of Marine Science 农林科学-海洋学

CiteScore

6.60

自引率

12.10%

发文量

207

审稿时长

6-16 weeks

期刊介绍： The ICES Journal of Marine Science publishes original articles, opinion essays (“Food for Thought”), visions for the future (“Quo Vadimus”), and critical reviews that contribute to our scientific understanding of marine systems and the impact of human activities on them. The Journal also serves as a foundation for scientific advice across the broad spectrum of management and conservation issues related to the marine environment. Oceanography (e.g. productivity-determining processes), marine habitats, living resources, and related topics constitute the key elements of papers considered for publication. This includes economic, social, and public administration studies to the extent that they are directly related to management of the seas and are of general interest to marine scientists. Integrated studies that bridge gaps between traditional disciplines are particularly welcome.